ChronodeAi · ChronodeAi · Aug 24, 2026 · Aug 2, 2026 · Aug 2, 2026 · Aug 24, 2026
diff --git a/.aiwg/reports/g-icm-01-interface-inventory.json b/.aiwg/reports/g-icm-01-interface-inventory.json
@@ -3,20 +3,20 @@
   "control_id": "G-ICM-01",
   "project_id": "github.com/chronodeai/agentmemory",
   "source_identity": {
-    "commit_sha": "c63d30d8a73c2606d3b1744d44bfebccf879aab4",
-    "commit_tree_sha": "6bc317c59fa693a3aabc96f9be2fa611ba8fb67f",
-    "inventory_input_sha256": "72e91136f073462267f8c40b3dbdd2bf0661992f0f992a9b73e0256bd3ec04c8"
+    "commit_sha": "f4d09d665ce361469d656d33c58fb7c3b9501c10",
+    "commit_tree_sha": "4030db14ef5d20729acb7ab5d3af6f89d2e88e9a",
+    "inventory_input_sha256": "a37239e57e45775e39143e539e5e620e5545f4a9c51e49bb4f5f6197ddf3e874"
   },
   "public_route_allowlist": [
     "GET /agentmemory/livez"
   ],
   "counts": {
-    "registered_api_functions": 136,
-    "http_routes": 135,
+    "registered_api_functions": 137,
+    "http_routes": 136,
     "public_routes": 1,
-    "protected_routes": 134,
+    "protected_routes": 135,
     "missing_auth_routes": 0,
-    "mcp_tools": 59,
+    "mcp_tools": 60,
     "mcp_transport_routes": 6,
     "mcp_resources": 5,
     "mcp_prompts": 3,
@@ -614,7 +614,7 @@
       "middleware": [],
       "registration": "protected-wrapper",
       "auth_control": "required",
-      "source": "src/triggers/api.ts:4637"
+      "source": "src/triggers/api.ts:4652"
     },
     {
       "surface_id": "REST:POST:/agentmemory/insights/search",
@@ -624,7 +624,7 @@
       "middleware": [],
       "registration": "protected-wrapper",
       "auth_control": "required",
-      "source": "src/triggers/api.ts:4659"
+      "source": "src/triggers/api.ts:4674"
     },
     {
       "surface_id": "REST:POST:/agentmemory/leases/acquire",
@@ -676,6 +676,16 @@
       "auth_control": "required",
       "source": "src/triggers/api.ts:4481"
     },
+    {
+      "surface_id": "REST:POST:/agentmemory/lessons/delete",
+      "method": "POST",
+      "path": "/agentmemory/lessons/delete",
+      "function_id": "api::lesson-delete",
+      "middleware": [],
+      "registration": "protected-wrapper",
+      "auth_control": "required",
+      "source": "src/triggers/api.ts:4582"
+    },
     {
       "surface_id": "REST:POST:/agentmemory/lessons/search",
       "method": "POST",
@@ -826,7 +836,7 @@
       "middleware": [],
       "registration": "protected-wrapper",
       "auth_control": "required",
-      "source": "src/triggers/api.ts:4584"
+      "source": "src/triggers/api.ts:4599"
     },
     {
       "surface_id": "REST:POST:/agentmemory/patterns",
@@ -902,7 +912,7 @@
       "middleware": [],
       "registration": "protected-wrapper",
       "auth_control": "required",
-      "source": "src/triggers/api.ts:4603"
+      "source": "src/triggers/api.ts:4618"
     },
     {
       "surface_id": "REST:GET:/agentmemory/relations",
@@ -1670,6 +1680,15 @@
       "project_parameter": false,
       "scope_parameter": false
     },
+    {
+      "surface_id": "MCP:TOOL:memory_lesson_delete",
+      "name": "memory_lesson_delete",
+      "required": [
+        "lessonId"
+      ],
+      "project_parameter": false,
+      "scope_parameter": false
+    },
     {
       "surface_id": "MCP:TOOL:memory_lesson_recall",
       "name": "memory_lesson_recall",
@@ -4006,7 +4025,7 @@
     {
       "surface_id": "REST:GET:/agentmemory/insights",
       "type": "rest",
-      "source": "src/triggers/api.ts:4637",
+      "source": "src/triggers/api.ts:4652",
       "auth_control": "required",
       "control_ids": [
         "ICM-08"
@@ -4026,7 +4045,7 @@
     {
       "surface_id": "REST:POST:/agentmemory/insights/search",
       "type": "rest",
-      "source": "src/triggers/api.ts:4659",
+      "source": "src/triggers/api.ts:4674",
       "auth_control": "required",
       "control_ids": [
         "ICM-08"
@@ -4158,6 +4177,26 @@
         "test/promotions.test.ts"
       ]
     },
+    {
+      "surface_id": "REST:POST:/agentmemory/lessons/delete",
+      "type": "rest",
+      "source": "src/triggers/api.ts:4582",
+      "auth_control": "required",
+      "control_ids": [
+        "ICM-08"
+      ],
+      "requirements": [
+        "FR-13",
+        "FR-14"
+      ],
+      "risks": [
+        "R-03",
+        "R-05"
+      ],
+      "tests": [
+        "test/promotions.test.ts"
+      ]
+    },
     {
       "surface_id": "REST:POST:/agentmemory/lessons/search",
       "type": "rest",
@@ -4497,7 +4536,7 @@
     {
       "surface_id": "REST:POST:/agentmemory/obsidian/export",
       "type": "rest",
-      "source": "src/triggers/api.ts:4584",
+      "source": "src/triggers/api.ts:4599",
       "auth_control": "required",
       "control_ids": [
         "ICM-04",
@@ -4661,7 +4700,7 @@
     {
       "surface_id": "REST:POST:/agentmemory/reflect",
       "type": "rest",
-      "source": "src/triggers/api.ts:4603",
+      "source": "src/triggers/api.ts:4618",
       "auth_control": "required",
       "control_ids": [
         "ICM-04",
@@ -6664,6 +6703,26 @@
         "test/integration.test.ts"
       ]
     },
+    {
+      "surface_id": "MCP:TOOL:memory_lesson_delete",
+      "type": "mcp-tool",
+      "source": "src/mcp/tools-registry.ts",
+      "auth_control": "transport-required",
+      "control_ids": [
+        "ICM-08"
+      ],
+      "requirements": [
+        "FR-13",
+        "FR-14"
+      ],
+      "risks": [
+        "R-03",
+        "R-05"
+      ],
+      "tests": [
+        "test/promotions.test.ts"
+      ]
+    },
     {
       "surface_id": "MCP:TOOL:memory_lesson_recall",
       "type": "mcp-tool",

diff --git a/AGENTS.md b/AGENTS.md
@@ -117,8 +117,8 @@ Hook scripts in `src/hooks/` are standalone Node.js scripts (no iii-sdk import).
 
 ## Current Stats (v0.9.28)
 
-- 59 MCP tools (`all` by default; 8 with `AGENTMEMORY_TOOLS=core`)
-- 135 REST endpoints
+- 60 MCP tools (`all` by default; 8 with `AGENTMEMORY_TOOLS=core`)
+- 136 REST endpoints
 - 6 MCP resources, 3 MCP prompts
 - 12 hooks, 15 skills (plus the standalone post-commit capture entrypoint)
 - 260+ iii functions

diff --git a/README.md b/README.md
@@ -47,7 +47,7 @@
 <p align="center">
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-recall.svg"><img src="assets/tags/stat-recall.svg" alt="95.2% retrieval R@5" height="38" /></picture>
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-tokens.svg"><img src="assets/tags/stat-tokens.svg" alt="92% fewer tokens" height="38" /></picture>
-  <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-tools.svg"><img src="assets/tags/stat-tools.svg" alt="59 MCP tools" height="38" /></picture>
+  <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-tools.svg"><img src="assets/tags/stat-tools.svg" alt="60 MCP tools" height="38" /></picture>
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-hooks.svg"><img src="assets/tags/stat-hooks.svg" alt="12 auto hooks" height="38" /></picture>
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-deps.svg"><img src="assets/tags/stat-deps.svg" alt="0 external DBs" height="38" /></picture>
   <picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/stat-tests.svg"><img src="assets/tags/stat-tests.svg" alt="1,428+ tests passing" height="38" /></picture>
@@ -504,7 +504,7 @@ Implementation details live in `src/cli.ts` (see `runUpgrade` around the `src/cl
 ### Claude Code (one block, paste it)
 
 ```text
-Install agentmemory: run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server. Then run `/plugin marketplace add rohitg00/agentmemory` and `/plugin install agentmemory` — the plugin registers all 12 hooks, 15 skills, AND auto-wires the `@agentmemory/mcp` stdio server via its `.mcp.json`, so you get 59 MCP tools (memory_smart_search, memory_save, memory_sessions, memory_governance_delete, etc.) without any extra config step. Verify with `curl http://localhost:3111/agentmemory/health`. The real-time viewer is at http://localhost:3113.
+Install agentmemory: run `npx @agentmemory/agentmemory` in a separate terminal to start the memory server. Then run `/plugin marketplace add rohitg00/agentmemory` and `/plugin install agentmemory` — the plugin registers all 12 hooks, 15 skills, AND auto-wires the `@agentmemory/mcp` stdio server via its `.mcp.json`, so you get 60 MCP tools (memory_smart_search, memory_save, memory_sessions, memory_governance_delete, etc.) without any extra config step. Verify with `curl http://localhost:3111/agentmemory/health`. The real-time viewer is at http://localhost:3113.
 ```
 
 #### Claude Code without the plugin install (MCP-standalone path)
@@ -955,9 +955,9 @@ npm install @xenova/transformers
 
 <h2 id="mcp-server"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-mcp.svg"><img src="assets/tags/section-mcp.svg" alt="MCP Server" height="32" /></picture></h2>
 
-59 tools, 6 resources, 3 prompts, and 15 skills, the most comprehensive MCP memory toolkit for any agent.
+60 tools, 6 resources, 3 prompts, and 15 skills, the most comprehensive MCP memory toolkit for any agent.
 
-> **MCP shim vs full server:** the published `@agentmemory/mcp` package is a thin shim. It exposes the full 58-tool surface **only when it can reach a running agentmemory server** via `AGENTMEMORY_URL` (proxy mode). With no server reachable, the shim falls back to a 7-tool local set (`memory_save`, `memory_recall`, `memory_smart_search`, `memory_sessions`, `memory_export`, `memory_audit`, `memory_governance_delete`). The `AGENTMEMORY_TOOLS=core|all` env var is a *server-side* flag — setting it in the shim's `env` block has no effect. If you see only 7 tools in Cursor / OpenCode / Gemini CLI, start `npx @agentmemory/agentmemory` (or the Docker stack) and set `AGENTMEMORY_URL=http://localhost:3111`.
+> **MCP shim vs full server:** the published `@agentmemory/mcp` package is a thin shim. It exposes the full 60-tool surface **only when it can reach a running agentmemory server** via `AGENTMEMORY_URL` (proxy mode). With no server reachable, the shim falls back to a 7-tool local set (`memory_save`, `memory_recall`, `memory_smart_search`, `memory_sessions`, `memory_export`, `memory_audit`, `memory_governance_delete`). The `AGENTMEMORY_TOOLS=core|all` env var is a *server-side* flag — setting it in the shim's `env` block has no effect. If you see only 7 tools in Cursor / OpenCode / Gemini CLI, start `npx @agentmemory/agentmemory` (or the Docker stack) and set `AGENTMEMORY_URL=http://localhost:3111`.
 
 ### 53 Tools
 
@@ -1503,7 +1503,7 @@ Create `~/.agentmemory/.env`:
 
 <h2 id="api"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/tags/light/section-api.svg"><img src="assets/tags/section-api.svg" alt="API" height="32" /></picture></h2>
 
-135 endpoints on port `3111`. The REST API binds to `127.0.0.1` by default.
+136 endpoints on port `3111`. The REST API binds to `127.0.0.1` by default.
 Only `/agentmemory/livez` is public. Protected endpoints, including detailed
 health telemetry, require `Authorization: Bearer <secret>`. Explicit
 cross-project `scope: "global"` requires the separate

diff --git a/assets/tags/light/stat-tools.svg b/assets/tags/light/stat-tools.svg
diff --git a/assets/tags/stat-tools.svg b/assets/tags/stat-tools.svg
diff --git a/ci/r13-test-manifest.json b/ci/r13-test-manifest.json
@@ -1,5 +1,5 @@
 {
   "count": 159,
   "sha256": "987f48c8beda0e67f96c4b16a60c5637cca072d2bb054493561a74fbf4e984b7",
-  "content_sha256": "75371c531f6b4a71fe2c6ea72e483bbb3005d570b8e680e88371ba928b3c1843"
+  "content_sha256": "5b4e61aba030ee6139c86f29cf7c2eccda3923cb959578b1aada8e67efee6184"
 }
diff --git a/plugin/.claude-plugin/plugin.json b/plugin/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "agentmemory",
   "version": "0.9.28-chronode.12",
-  "description": "Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 59 MCP tools, 15 skills, real-time viewer.",
+  "description": "Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 60 MCP tools, 15 skills, real-time viewer.",
   "author": {
     "name": "Rohit Ghumare",
     "url": "https://github.com/rohitg00"

diff --git a/plugin/.codex-plugin/plugin.json b/plugin/.codex-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "agentmemory",
   "version": "0.9.28-chronode.12",
-  "description": "Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 11 hooks, 59 MCP tools, 15 skills, real-time viewer.",
+  "description": "Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 11 hooks, 60 MCP tools, 15 skills, real-time viewer.",
   "author": {
     "name": "Rohit Ghumare",
     "url": "https://github.com/rohitg00"

diff --git a/plugin/plugin.json b/plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "agentmemory",
   "version": "0.9.28-chronode.12",
-  "description": "Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 59 MCP tools, 15 skills, real-time viewer.",
+  "description": "Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 60 MCP tools, 15 skills, real-time viewer.",
   "author": {
     "name": "Rohit Ghumare",
     "url": "https://github.com/rohitg00"

diff --git a/plugin/scripts/standalone.mjs b/plugin/scripts/standalone.mjs
@@ -1306,6 +1306,18 @@ const V070_TOOLS = [
 			required: ["query"]
 		}
 	},
+	{
+		name: "memory_lesson_delete",
+		description: "Soft-delete a lesson by id. Deleted lessons are excluded from recall and list; re-saving the same content creates a fresh lesson.",
+		inputSchema: {
+			type: "object",
+			properties: { lessonId: {
+				type: "string",
+				description: "The lesson id (lsn_...)"
+			} },
+			required: ["lessonId"]
+		}
+	},
 	{
 		name: "memory_obsidian_export",
 		description: "Export memories, lessons, and crystals as Obsidian-compatible Markdown files with YAML frontmatter and wikilinks for graph view.",
@@ -2032,10 +2044,16 @@ const READ_ONLY_LOCAL_FALLBACK_TOOLS = new Set([
 	"memory_export",
 	"memory_audit"
 ]);
+const SUPPORTED_PROTOCOL_VERSIONS = [
+	"2025-11-25",
+	"2025-06-18",
+	"2025-03-26",
+	"2024-11-05"
+];
 const SERVER_INFO = {
 	name: "agentmemory",
 	version: VERSION,
-	protocolVersion: "2024-11-05"
+	protocolVersion: SUPPORTED_PROTOCOL_VERSIONS[0]
 };
 function getStandalonePersistPath() {
 	return process.env["STANDALONE_PERSIST_PATH"]?.trim() || join(homedir(), ".agentmemory", "standalone.json");
@@ -2388,14 +2406,17 @@ async function finishShutdown() {
 }
 const transport = createStdioTransport(async (method, params) => {
 	switch (method) {
-		case "initialize": return {
-			protocolVersion: SERVER_INFO.protocolVersion,
-			capabilities: { tools: { listChanged: false } },
-			serverInfo: {
-				name: SERVER_INFO.name,
-				version: SERVER_INFO.version
-			}
-		};
+		case "initialize": {
+			const requested = params?.protocolVersion;
+			return {
+				protocolVersion: typeof requested === "string" && SUPPORTED_PROTOCOL_VERSIONS.includes(requested) ? requested : SERVER_INFO.protocolVersion,
+				capabilities: { tools: { listChanged: false } },
+				serverInfo: {
+					name: SERVER_INFO.name,
+					version: SERVER_INFO.version
+				}
+			};
+		}
 		case "notifications/initialized": return {};
 		case "tools/list": return handleToolsList();
 		case "tools/call": {

diff --git a/plugin/skills/agentmemory-mcp-tools/REFERENCE.md b/plugin/skills/agentmemory-mcp-tools/REFERENCE.md
@@ -3,7 +3,7 @@
 Generated from `src/mcp/tools-registry.ts`. Do not edit the block below by hand; run `npm run skills:gen` after changing the registry.
 
 <!-- AUTOGEN:tools START - generated by scripts/skills/generate.ts, do not edit by hand -->
-agentmemory exposes 59 MCP tools. 8 are in the lean core set (`--tools core` or `AGENTMEMORY_TOOLS=core`); the rest load with `--tools all` (default).
+agentmemory exposes 60 MCP tools. 8 are in the lean core set (`--tools core` or `AGENTMEMORY_TOOLS=core`); the rest load with `--tools all` (default).
 
 | Tool | Core | Parameters | Purpose |
 | --- | --- | --- | --- |
@@ -31,6 +31,7 @@ agentmemory exposes 59 MCP tools. 8 are in the lean core set (`--tools core` or
 | `memory_heal` |  | `categories`: string, `dryRun`: string | Auto-fix all fixable issues found by diagnostics. Unblocks stuck actions, expires stale leases, cleans up orphaned data. |
 | `memory_insight_list` |  | `project`: string, `scope`: string, `minConfidence`: number, `limit`: number | List synthesized insights, higher-order observations derived from patterns across memories, lessons, and crystals. |
 | `memory_lease` |  | `actionId`*: string, `agentId`*: string, `operation`*: string, `result`: string, `ttlMs`: number | Acquire, release, or renew an exclusive lease on an action. Prevents multiple agents from working on the same thing. |
+| `memory_lesson_delete` |  | `lessonId`*: string | Soft-delete a lesson by id. Deleted lessons are excluded from recall and list; re-saving the same content creates a fresh lesson. |
 | `memory_lesson_recall` |  | `query`*: string, `project`: string, `scope`: string, `minConfidence`: number, `limit`: number | Search lessons by query. Returns lessons sorted by confidence and recency. Use to check what the agent has learned before making decisions. |
 | `memory_lesson_save` | yes | `content`*: string, `context`: string, `confidence`: number, `project`: string, `scope`: string, `tags`: string | Save a lesson learned from this session. Lessons have confidence scores that strengthen when reinforced and decay when not used. Duplicate content auto-strengthens the existing lesson. |
 | `memory_mesh_sync` |  | `peerId`: string, `direction`: string | Sync memories and actions with peer agentmemory instances for multi-agent collaboration. |

diff --git a/plugin/skills/agentmemory-rest-api/REFERENCE.md b/plugin/skills/agentmemory-rest-api/REFERENCE.md
@@ -5,7 +5,7 @@ Generated from `src/triggers/api.ts`. Do not edit the block below by hand; run `
 <!-- AUTOGEN:rest START - generated by scripts/skills/generate.ts, do not edit by hand -->
 The REST API is the primary surface. All paths are under `http://localhost:3111` (override with `--port`). When `AGENTMEMORY_SECRET` is set, send `Authorization: Bearer $AGENTMEMORY_SECRET`; localhost is otherwise open.
 
-124 registered endpoints:
+125 registered endpoints:
 
 | Method | Path |
 | --- | --- |
@@ -68,6 +68,7 @@ The REST API is the primary surface. All paths are under `http://localhost:3111`
 | POST | `/agentmemory/leases/release` |
 | POST | `/agentmemory/leases/renew` |
 | POST | `/agentmemory/lessons` |
+| POST | `/agentmemory/lessons/delete` |
 | POST | `/agentmemory/lessons/search` |
 | POST | `/agentmemory/lessons/strengthen` |
 | GET | `/agentmemory/livez` |